The cost of caring about software - Alex Rios Substack

kept by noorjehan aug 21

AI reduces code-writing effort but shifts verification cost onto reviewers, creating an externality where comprehension debt rises despite faster generation.

advanced-context-engineering-for-coding-agents/wsff.md at main · humanlayer/advanced-context-engineering-for-coding-agents
AI coding agents alone can't sustain high-quality software factories because model limitations and review bottlenecks remain, requiring better context engineering rather than just more loops.
also on Faros AI, #ai-coding, #software-engineering, #productivity, #developer-tools
The 80% Problem in Agentic Coding - by Addy Osmani
Addy Osmani argues that while AI agents now write 80% of code for early adopters, this shifts problems to "comprehension debt," where developers understand less of their own codebases.
also on Faros AI, #ai-coding, #software-engineering, #productivity, #developer-tools
Let’s talk about LLMs
LLMs do not provide a revolutionary productivity gain in software development because the essential difficulty lies in specification, design, and testing, not code generation speed.
also on DORA, Cursor, #ai-coding, #software-engineering, #productivity, #developer-tools
The Productivity-Experience Paradox - Annie Vella
AI coding assistants boost engineers’ perceived productivity while eroding developer experience, especially flow state, revealing a growing decoupling of output and inner work satisfaction.
also on DORA, #ai-coding, #software-engineering, #productivity, #developer-tools
The Evolution of the Agent Harness - by Dan McAteer
The article argues that as AI models internalize agent harness capabilities, the remaining harness evolves into an interface for managing scarce human attention rather than directing model behavior.
also on Copilot, Cursor, #ai-coding, #software-engineering, #developer-tools